Akademik Veri Yönetim Sistemi
2025 33rd Signal Processing and Communications Applications Conference (SIU), İstanbul, Türkiye, 25 - 28 Haziran 2025, ss.1-4, (Tam Metin Bildiri)
Image segmentation is an image processing method that aims to separate objects or regions within an image by dividing the image into meaningful parts. Threshold, one of the segmentation methods, separates the object or region from the background of the image by classifying pixels according to a certain threshold value. Otsu method is one of the most popular methods for segmentation. It determines the optimal threshold values by maximizing the variance between classes. However, adapting the Otsu to the multi-level image segmentation requires more computational time. Therefore, meta-heuristics that provide simple solutions to complex optimization problems have been used in image segmentation. In this study, the tuna swarm optimization is improved with the opposition-based learning strategy and used for segmentation of brain MRI images. The proposed algorithm is compared with different algorithms based on Otsu objective function and its superiority over others is demonstrated.